Instructions to use MESHIVEAI/qwen2.5-0.5b-pirate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MESHIVEAI/qwen2.5-0.5b-pirate with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MESHIVEAI/qwen2.5-0.5b-pirate")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MESHIVEAI/qwen2.5-0.5b-pirate")
model = AutoModelForCausalLM.from_pretrained("MESHIVEAI/qwen2.5-0.5b-pirate", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MESHIVEAI/qwen2.5-0.5b-pirate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MESHIVEAI/qwen2.5-0.5b-pirate"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MESHIVEAI/qwen2.5-0.5b-pirate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MESHIVEAI/qwen2.5-0.5b-pirate

SGLang

How to use MESHIVEAI/qwen2.5-0.5b-pirate with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MESHIVEAI/qwen2.5-0.5b-pirate" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MESHIVEAI/qwen2.5-0.5b-pirate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MESHIVEAI/qwen2.5-0.5b-pirate" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MESHIVEAI/qwen2.5-0.5b-pirate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MESHIVEAI/qwen2.5-0.5b-pirate with Docker Model Runner:
```
docker model run hf.co/MESHIVEAI/qwen2.5-0.5b-pirate
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🏴‍☠️ Qwen2.5-0.5B-Pirate

Ahoy, matey! ⚓ This model is a highly efficient and extremely fast Qwen2.5-0.5B-Instruct, fine-tuned to answer all your prompts like a true, swashbuckling pirate of the seven seas!

Whether you need coding help, daily advice, or just a good sea shanty, this model will deliver it with a hearty "Arrr!" Thanks to its ultra-lightweight 0.5B parameter size, it runs at lightning speed on almost any device.

🌟 Model Details

Base Model: Qwen/Qwen2.5-0.5B-Instruct
Parameters: 0.5 Billion (Extremely lightweight & fast!)
Intended Use: Roleplay, creative writing, entertainment, and fast local inference.
Format: ChatML (Standard Qwen prompt format)

🚀 How to Get Started

You can easily set sail with this model using the transformers library.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "meshive/qwen2.5-0.5b-pirate"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "system", "content": "You are a fierce and loyal pirate captain."},
    {"role": "user", "content": "Can you write a Python script to print the multiplication table?"}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Downloads last month: 13

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for MESHIVEAI/qwen2.5-0.5b-pirate

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(1011)

this model

Quantizations

1 model